Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.8024. Min Act: -0.0000

Data Index: 1774875 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7574. Min Act: -0.0000

Data Index: 171024 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.8302. Min Act: -0.0000

Data Index: 903018 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.4702. Min Act: -0.0000

Data Index: 887614 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6496. Min Act: -0.0000

Data Index: 1301645 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7240. Min Act: -0.0000

Data Index: 1855552 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.3776. Min Act: -0.0000

Data Index: 1538028 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5030. Min Act: -0.0000

Data Index: 1051218 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.3569. Min Act: -0.0000

Data Index: 1202723 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.3587. Min Act: -0.0000

Data Index: 1935065 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.3520. Min Act: -0.0000

Data Index: 884172 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.2642. Min Act: -0.0000

Data Index: 1556872 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.4245. Min Act: -0.0000

Data Index: 912160 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.2081. Min Act: -0.0000

Data Index: 1018473 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1567159 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.0658. Min Act: -0.0000

Data Index: 1015647 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5085. Min Act: -0.0000

Data Index: 1103901 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.1737. Min Act: -0.0000

Data Index: 1659859 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.1574. Min Act: -0.0000

Data Index: 1481069 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.0129. Min Act: -0.0000

Data Index: 1733650 (The Pile)

Max Activating Token Index: 989